Dataset Information

The use of electronic healthcare records for colorectal cancer screening referral decisions and risk prediction model development.

ABSTRACT:

Background

The database used for the NHS Bowel Cancer Screening Programme (BCSP) derives participant information from primary care records. Combining predictors with FOBTs has shown to improve referral decisions and accuracy. The richer data available from GP databases could be used to complement screening referral decisions by identifying those at greatest risk of colorectal cancer. We determined the availability of data for key predictors and whether this information could be used to inform more accurate screening referral decisions.

Methods

An English BCSP cohort was derived using the electronic notifications received from the BCSP database to GP records. The cohort covered a period between 13th May 2009 to 17th January 2017. Completeness of variables and univariable associations were assessed. Risk prediction models were developed using Cox regression and multivariable fractional polynomials with backwards elimination. Optimism adjusted performance metrics were reported. The sensitivity and specificity of a combined approach using the negative FOBT model plus FOBT positive patients was determined using a probability equivalent to a 3% PPV NICE guidelines level.

Results

292,059 participants aged 60-74 were derived for the BCSP screening cohort. A model including the screening test result had a C-statistic of 0.860, c-slope of 0.997, and R² of 0.597. A model developed for negative screening results only had a C-statistic of 0.597, c-slope of 0.940, and R² of 0.062. Risk predictors included in the models included; age, sex, alcohol consumption, IBS diagnosis, family history of gastrointestinal cancer, smoking status, previous negatives and whether a GP had ordered a blood test. For the combined screening approach, sensitivity increased slightly from 53.90% (FOBT only) to 58.82% but at the expense of an increased referral rate.

Conclusions

This research has identified several potential predictors for CRC in a BCSP population. A risk prediction model developed for BCSP FOBT negative patients was not clinically useful due to a low sensitivity and increased referral rate. The predictors identified in this study should be investigated in a refined algorithm combining the quantitative FIT result. Combining data from multiple sources enables fuller patient profiles using the primary care and screening database interface.

SUBMITTER: Cooper JA

PROVIDER: S-EPMC7093989 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background: People who use illicit opioids such as heroin have substantial health needs, but there are few longitudinal studies of general health and healthcare in this population. Most research to date has focused on a narrow set of outcomes, including overdoses and HIV or hepatitis infections. We developed and validated a cohort using UK primary care electronic health records (Clinical Practice Research Datalink GOLD and AURUM databases) to facilitate research into healthcare use by people who use illicit opioid use (HUPIO). Methods: Participants are patients in England with primary care records indicating a history of illicit opioid use. We identified codes including prescriptions of opioid agonist therapies (methadone and buprenorphine) and clinical observations such as 'heroin dependence'. We constructed a cohort of patients with at least one of these codes and aged 18-64 at cohort entry, with follow-up between January 1997 and March 2020. We validated the cohort by comparing patient characteristics and mortality rates to other cohorts of people who use illicit opioids, with different recruitment methods. Results: Up to March 2020, the HUPIO cohort included 138,761 patients with a history of illicit opioid use. Demographic characteristics and all-cause mortality were similar to existing cohorts: 69% were male; the median age at index for patients in CPRD AURUM (the database with more included participants) was 35.3 (interquartile range 29.1-42.6); the average age of new cohort entrants increased over time; 76% had records indicating current tobacco smoking; patients disproportionately lived in deprived neighbourhoods; and all-cause mortality risk was 6.6 (95% CI 6.5-6.7) times the general population of England. Conclusions: Primary care data offer new opportunities to study holistic health outcomes and healthcare of this population. The large sample enables investigation of rare outcomes, whilst the availability of linkage to external datasets allows investigation of hospital use, cancer treatment, and mortality.

Project description:ObjectiveTo provide focused evaluation of predictive modeling of electronic medical record (EMR) data to predict 30 day hospital readmission.DesignSystematic review.Data sourceOvid Medline, Ovid Embase, CINAHL, Web of Science, and Scopus from January 2015 to January 2019.Eligibility criteria for selecting studiesAll studies of predictive models for 28 day or 30 day hospital readmission that used EMR data.Outcome measuresCharacteristics of included studies, methods of prediction, predictive features, and performance of predictive models.ResultsOf 4442 citations reviewed, 41 studies met the inclusion criteria. Seventeen models predicted risk of readmission for all patients and 24 developed predictions for patient specific populations, with 13 of those being developed for patients with heart conditions. Except for two studies from the UK and Israel, all were from the US. The total sample size for each model ranged between 349 and 1 195 640. Twenty five models used a split sample validation technique. Seventeen of 41 studies reported C statistics of 0.75 or greater. Fifteen models used calibration techniques to further refine the model. Using EMR data enabled final predictive models to use a wide variety of clinical measures such as laboratory results and vital signs; however, use of socioeconomic features or functional status was rare. Using natural language processing, three models were able to extract relevant psychosocial features, which substantially improved their predictions. Twenty six studies used logistic or Cox regression models, and the rest used machine learning methods. No statistically significant difference (difference 0.03, 95% confidence interval -0.0 to 0.07) was found between average C statistics of models developed using regression methods (0.71, 0.68 to 0.73) and machine learning (0.74, 0.71 to 0.77).ConclusionsOn average, prediction models using EMR data have better predictive performance than those using administrative data. However, this improvement remains modest. Most of the studies examined lacked inclusion of socioeconomic features, failed to calibrate the models, neglected to conduct rigorous diagnostic testing, and did not discuss clinical impact.